© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 6522
    Prev
    Next
    INDEX
    Explanations

    phrases related to punishment or reprimand, particularly involving the concept of a 'slap'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word 'slap' and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Belief
    -0.81
    inventoryQuantity
    -0.74
    quickShipAvailable
    -0.72
    natureconservancy
    -0.71
    Govern
    -0.68
     Correspond
    -0.67
     Continued
    -0.67
    VIEW
    -0.66
    tis
    -0.65
     Leaders
    -0.65
    POSITIVE LOGITS
     slap
    1.23
     slapped
    1.16
    stick
    1.07
     slapping
    1.06
    dash
    1.01
    bowl
    0.85
    gery
    0.85
    creen
    0.84
     dab
    0.81
     elbows
    0.81
    Activations Density 0.009%

    No Known Activations